Comparison of generative and discriminative techniques for object detection and classification

Date

2004-01-01

Author

Ulusoy, İlkay

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

192
views

0
downloads

Many approaches to object recognition are founded on probability theory, and can be broadly characterized as either generative or discriminative according to whether or not the distribution of the image features is modelled. Generative and discriminative methods have very different characteristics, as well as complementary strengths and weaknesses. In this chapter we introduce new generative and discriminative models for object detection and classification based on weakly labelled training data. We use these models to illustrate the relative merits of the two approaches in the context of a data set of widely varying images of non-rigid objects (animals). Our results support the assertion that neither approach alone will be sufficient for large scale object recognition, and we discuss techniques for combining the strengths of generative and discriminative approaches.

Subject Keywords

Scale

URI

https://hdl.handle.net/11511/53646

DOI

https://doi.org/10.1007/11957959_9

Collections

Department of Electrical and Electronics Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

A generative model for multi class object recognition and detection Ulusoy, İlkay (2006-01-01) In this study, a generative type probabilistic model is proposed for object recognition. This model is trained by weakly labelled images and performs classification and detection at the same time. When test on highly challenging data sets, the model performs good for both tasks (classification and detection).
Generative versus discriminative methods for object recognition Ulusoy, İlkay (2005-06-25) Many approaches to object recognition are founded on probability theory, and can be broadly characterized as either generative or discriminative according to whether or not the distribution of the image features is modelled. Generative and discriminative methods have very different characteristics, as well as complementary strengths and weaknesses. In this paper we introduce new generative and discriminative models for object detection and classification based on weakly labelled training data. We use these ...
Object Recognition via Local Patch Labelling Ulusoy, İlkay (2005-03-01) In recent years the problem of object recognition has received considerable attention from both the machine learning and computer vision communities. The key challenge of this problem is to be able to recognize any member of a category of objects in spite of wide variations in visual appearance due to variations in the form and colour of the object, occlusions, geometrical transformations (such as scaling and rotation), changes in illumination, and potentially non-rigid deformations of the object itself. In...
Multiscale method for feature preserving compression Tarı, Zehra Sibel (1998-01-01) Requirements fora good shape representation lead to descriptors that are object centered and that have the notion of scale. These representations usually take the form of shape skeletons at multiple detail levels. Classical tool for skeleton extraction is the grassfire equation, in which the process is lossless and the equation can be run backwards in order to obtain shape boundary from the shape skeleton. Many complicated strategies have been devised to assign significance to skeletal points in order to ar...
Comparison of two inference approaches in Gaussian graphical models Purutçuoğlu Gazi, Vilda; Wit, Ernst (Walter de Gruyter GmbH, 2017-04-01) Introduction: The Gaussian Graphical Model (GGM) is one of the well-known probabilistic models which is based on the conditional independency of nodes in the biological system. Here, we compare the estimates of the GGM parameters by the graphical lasso (glasso) method and the threshold gradient descent (TGD) algorithm.

Citation Formats

İ. Ulusoy, “Comparison of generative and discriminative techniques for object detection and classification,” 2004, vol. 4170, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/53646.